The Study of Dialogue

Only available on StudyMode
  • Download(s) : 504
  • Published : June 7, 2012
Open Document
Text Preview
MINISTERUL EDUCAŢIEI, CERCETĂRII, TINERETULUI ŞI SPORTULUI UNIVERSITATEA „1 DECEMBRIE 1918” ALBA IULIA
FACULTATEA DE ISTORIE ŞI FILOLOGIE
SPECIALIZAREA: LIMBĂ ŞI COMUNICARE ÎN ADMINISTRAREA AFACERILOR

COMPUTATIONAL LINGUISTICS

MASTERAND: OROIAN CRISTINA OANA

An II, Sem. Al II-lea

ALBA IULIA

2011

Analyzing Dialogue

To begin with, I will give a definition of the Dialogue provided by the Encyclopedia Britannica, 2008:

Dialogue – 1. Conversation between two or more persons.

2. The conversation between characters in a novel, drama, etc.

3. An exchange of ideas or opinions on a particular issue, especially a political or religious issue, with a view to reaching an amicable agreement or settlement.

4. A literary work in the form of a conversation: a dialogue of Plato.

The study of dialog is of practical interest because most current applications of natural language processing involve man-machine interaction: question-answering systems and natural language command system for example. These systems will be most effective only if we are able to understand and use in our programs the techniques which people employ in conversation. Most currently implemented systems use only the simplest dialog structure, with unilateral initiative. In such a system, one party completely controls the conversation, giving commands or asking questions; the other party simply responds to the last command or question. In a computerized interviewing system (i.e. collecting patient histories) the computer would ask questions and the user would respond to them one-by-one. In a question-answering system, the user will pose the questions and the system would respond to each in turn. Such systems are relatively simply to implement, since they need not analyze the structure of proceeding dialog. Preparing to Analyze a Dialogue:

Details of preparation will depend on the purposes of the analyst, but there are certainly some recurrent needs. • The circumstances of the dialogue, occasion of talk, and something about the immediate culture, language, and organizational context need to be known. • Whether the participants have interacted before, and the outcomes of the most recent interaction (relationships, obligations, fixed knowledge) need to be known. • The method and media of recording need to be known. If there are multiple media, (e.g. transcript, audio, video...) all need to be known and considered together. For multimedia, the usefulness of doing an initial transcript-only analysis should be considered. • The researchers' rights in sharing and publishing any results need to be known at the outset. Often the amount of information needed is quite small, but having some information of each kind is generally essential. Some division of the dialogue into units of analysis is needed. To prevent circularity of methods, it is best to identify the units before analyzing. This raises various problems for collections of dialogues; see below. For the particular purposes of developing DMT (Dialogue Macrogame Theory), one of the goals is to develop a broad based collection of macrogames. Because the dynamics of dialogue varies a great deal with the situation, especially the obligations, tasks, status and expectations of the participants, a broad sampling of dialogue situations is needed. This requires moving beyond controlled laboratory settings and accessing dialogues from diverse sources. Diversity of sources leads to a strong desire for flexibility in the analysis tools and conventions. There is a great advantage in analyzing dialogues in some form easily derived from available forms. On the other hand, for the purpose of sharing of data and results, uniform, widely used representations are desirable. For DMT this tension is still unresolved, and the...
tracking img